knowledge_search

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Even though readOnlyHint=true is already in annotations, the description adds substantial behavioral context: whitespace-splitting, AND logic across tokens, the `limit` cap on returns, and the `domain` narrowing behavior. These details (especially the AND semantics) go well beyond what the annotations provide and meaningfully inform the caller about expected behavior. The description is consistent with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description uses three sentences with no fluff: first stating the primary purpose, then behavioral details, and finally routing to the alternative. Each sentence earns its place and the most critical information (what and how) is front-loaded. The mention of 'fleet' and example domain values add necessary context without bloat.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool without an output schema or nested objects, the description covers the key aspects: what is searched (fleet Postgres knowledge base), how matching works (AND logic), the role of each parameter it mentions, and which sibling to use instead. The main gap is the undocumented `app_id` parameter and the complete absence of any note about the return format of the search results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description carries the full burden and does explain `domain` (narrows to one domain) and `limit` (returns up to that many). However, `app_id` is a required field that gets no mention at all, which is a gap since the agent must provide it. The query parameter is only implied by 'by content' rather than explicitly described.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource ('Search the fleet Postgres knowledge base by content') and distinguishes itself from sibling kb_at by explicitly directing users to 'use kb_at to fetch a known atom by ID'. It clearly identifies what makes this search different from simple ID lookup. This is not a restatement of the tool name but a genuine functional explanation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides an explicit alternative (kb_at for fetching by ID) and implies when this tool is appropriate (when searching by content rather than known ID). The 'Read-only; use kb_at to fetch a known atom by ID' sentence explicitly routes the agent based on use case. This gives clear guidance on tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.